{"id":"W4409672176","doi":"10.1016/j.engappai.2025.110791","title":"Autonomous control of soft robots using safe reinforcement learning and covariance matrix adaptation","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Soft Robotics and Applications","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Adaptation (eye); Reinforcement learning; Robot; CMA-ES; Artificial intelligence; Covariance matrix; Control (management); Matrix (chemical analysis); Machine learning; Algorithm; Covariance function; Materials science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001261455,0.0001172721,0.0001837755,0.0001654726,0.00006480073,0.0000173171,0.0001239095,0.00006014864,0.000009234534],"category_scores_gemma":[0.00004637577,0.0001451029,0.00003679228,0.0004450065,0.00004794927,0.00005457434,0.00002231836,0.0001195029,0.000003818221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004436842,"about_ca_system_score_gemma":0.00003062812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003498145,"about_ca_topic_score_gemma":0.000002178147,"domain_scores_codex":[0.9991496,0.000005436155,0.0004782775,0.0001439906,0.00008546469,0.0001372012],"domain_scores_gemma":[0.9994386,0.0001561835,0.00008036576,0.0001872307,0.0001018879,0.0000357405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002838697,0.00001307889,0.00002728909,0.00009512861,0.00002779792,4.791078e-8,0.00008289742,0.876303,0.02754484,0.08053511,0.00000168319,0.01536632],"study_design_scores_gemma":[0.00002876673,0.00001074232,0.00004719959,0.00005209284,0.00003272203,7.081587e-7,0.00009572374,0.9708326,0.02729153,0.001026479,0.0004794465,0.000101945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004014372,0.0005471202,0.9947519,0.0000319354,0.00005513366,0.0003558255,0.000004979438,0.0001140806,0.0001247113],"genre_scores_gemma":[0.9372045,0.0000567502,0.06256236,0.000002995739,0.00002244856,0.00009978447,0.000005871361,0.00001469558,0.00003061201],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9331901,"threshold_uncertainty_score":0.5917122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01520364132953954,"score_gpt":0.26902420755714,"score_spread":0.2538205662276004,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}